王鹏焜，中国科大软件学院特任副研究员，硕士生导师。2017年本科毕业于吉林大学软件学院，2023年博士毕业于中国科学技术大学大数据学院。主要研究方向为数据挖掘、开放环境机器学习、AI4Science等，致力于提升深度学习模型的泛化性与鲁棒性，并应用于交叉学科（城市科学、化学材料）等开放场景，推动深度学习模型快速落地。近年来主持中国科学技术大学软件学院青年创新基金项目一项，作为技术骨干参与包括中国科学院抢占科技制高点攻坚专项、国家自然科学基金国家重大科研仪器研制项、中国科学院稳定支持基础研究领域青年团队计划等在内的多个项目。近五年来在包括人工智能领域的顶级国际学术会议/期刊IEEE TKDE、ICML、ICLR、WWW、AAAI、IJCAI、KDD 等在内的高水平国际会议和期刊上发表论文30余篇，其中以第一/通讯作者身份发表10余篇。多次担任ICML、NeurIPS、ICLR、KDD、AAAI、IJCAI、WWW等重要国际学术会议程序委员，担任Scientific Reports、Cluster Computing等多个国内外学术刊物审稿人。

电子邮箱：

pengkun@ustc.edu.cn

联系地址：

个人主页：

主要研究方向

开放环境数据挖掘和模型泛化

-          非理想数据分布：不平衡/长尾学习和分布外（OOD）泛化

-          动态数据分布：持续学习

-          稀疏数据分布：可解释的数据增强

-          可变学习目标：多目标优化

泛化AI4Science

-            城市交通：时空数据挖掘

-            化学材料：谱-效关系学习

-            半导体：智能电子设计自动化

学术论文及著作

[1]     [ICML 2024] Zhe Zhao, Pengkun Wang*, Haibin Wen, Wei Xu, Lai Song, Qingfu Zhang, Yang Wang*, Two Fists, One Heart: Multi-Objective Optimization Based Strategy Fusion for Long-tailed Learning, International Conference on Machine Learning, 2024. (CCF-A)

[2]     [IJCAI 2024] Binwu Wang, Pengkun Wang*, Zhengyang Zhou, Zhe Zhao, Wei Xu, Yang Wang*, Make Bricks With A Little Straw: Large-Scale Spatio-temporal Graph Learning with Restricted GPU-Memory Capacity, International Joint Conference on Artificial Intelligence, 2024. (CCF-A)

[3]     [WWW 2024] Wei Xu, Pengkun Wang*, Zhe Zhao, Binwu Wang, Xu Wang, Yang Wang*, When Imbalance Meets Imbalance: Structure-driven Learning for Imbalanced Graph Classification, The Web Conference, 2024. (CCF-A)

[4]     [ICLR 2024] Binwu Wang, Pengkun Wang*, Wei Xu, Xu Wang, Yudong Zhang, Kun Wang, Yang Wang*, Kill Two Birds with One Stone: Rethinking Data Augmentation for Deep Long-tailed Learning, International Conference on Learning Representations, 2024. (清华-A)

[5]     [AAAI 2024] Zhe Zhao, Pengkun Wang*, Haibin Wen, Yudong Zhang, Zhengyang Zhou, Yang Wang*, A Twist for Graph Classification: Optimizing Causal Information Flow in Graph Neural Networks, AAAI Conference on Artificial Intelligence, 2024. (CCF-A)

[6]     [AAAI 2024] Binwu Wang, Pengkun Wang*, Yudong Zhang, Xu Wang, Zhengyang Zhou, Lei Bai, Yang Wang*, Towards Dynamic Spatial-Temporal Graph Learning: A Decoupled Perspective, AAAI Conference on Artificial Intelligence, 2024. (CCF-A)

[7]     [ICASSP 2024] Zhe Zhao, Pengkun Wang*, Haibin Wen, Yudong Zhang, Binwu Wang, Yang Wang*, Graph Networks Stand Strong: Enhancing Robustness via Stability Constraints, IEEE International Conference on Acoustics, Speech and Signal Processing, 2024. (CCF-B)

[8]     [IEEE TVT] Binwu Wang, Pengkun Wang*, Yudong Zhang, Xu Wang, Zhengyang Zhou, Yang Wang*, Condition-Guided Urban Traffic Co-Prediction with Multiple Sparse Urban Data, IEEE Transactions on Vehicular Technology, 2024. (JCR一区/Top)

[9]     [IEEE TKDE] Pengkun Wang, Chuancai Ge, Zhengyang Zhou, Xu Wang, Yuantao Li, Yang Wang*, Joint Gated Co-attention Based Multi-modal Networks for Subregion House Price Prediction, IEEE Transactions on Knowledge and Data Engineering, 2023, 35(02): 1667-1680. (CCF-A)

[10] [DASFAA 2023] Pengkun Wang, Xu Wang, Binwu Wang, Yudong Zhang, Lei Bai*, Yang Wang*, Long-tailed Time Series Classification via Feature Space Rebalancing, The International Conference on Database Systems for Advanced Applications, 2023. (CCF-B)

[11] [ICASSP 2023] Yudong Zhang, Wei Lu, Xu Wang, Pengkun Wang*, Yang Wang*, Pondering about Task Spatial Misalignment: Classification-Localization Equilibrated Object Detection, IEEE International Conference on Acoustics, Speech and Signal Processing, 2023. (CCF-B)

[12] [IEEE TVT] Pengkun Wang, Chaochao Zhu, Xu Wang, Zhengyang Zhou, Guang Wang, Yang Wang*, Inferring Intersection Traffic Patterns with Sparse Video Surveillance Information: An ST-GAN Method, IEEE Transactions on Vehicular Technology, 2022. (JCR一区/Top)

[13] [ICDM 2022] Pengkun Wang, Xu Wang, Binwu Wang, Yudong Zhang, Lei Bai*, Yang Wang*, Countering Modal Redundancy and Heterogeneity: A Self-Correcting Multimodal Fusion, IEEE International Conference on Data Mining, 2022. (CCF-B)